Colivara is a suite of services that allows you to store, search, and retrieve documents based on their visual embedding. ColiVara has state of the art retrieval performance on both text and visual documents. using vision models instead of chunking and text-processing for documents. No OCR, no text extraction, no broken tables, or missing images.
Repository Index
104,105 visible repositories in the index
289–312 of 571 · Most stars
In the evolving world of Large Language Models (LLMs), crafting effective prompts has become an essential skill. That's why I've created this collection, showcasing the most impactful prompts of the year across various intriguing domains. 🌐
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
- apple-silicon
- deep-learning
- huggingface
- large-language-models
tl/dw (Too Long, Didn't Watch): Your Personal Research Multi-Tool - a naive attempt at 'A Young Lady's Illustrated Primer' (Open Source NotebookLM)
- ai-assistant
- ai-ml
- llm
- multi-tool
Jev-compatible API server for open decision models. Ollama for decision models: pull and serve 29 model families (Laya, pplx-decider, Clef, Winnow, coba...) locally or self-hosted behind /v1/systemone. The TypeSafe SDK works unchanged: set its base URL and pick an open model. CLI, desktop app, Docker, MCP server, public bench.
- decision-models
- jev
- laya
- local-inference
🌌 Give a soul to your favorite characters. Soul of Waifu is a desktop roleplay & AI companion app featuring Live2D/VRM avatars, voice chat & local LLM. Evolve together across immersive chat, RPG adventures, and your desktop.
- ai
- ai-girlfriend
- ai-waifu
- character-ai
tiny AI companions that live on your macOS dock
TokenHub gives enterprises a private gateway to unify AI model access and governance, making every request controllable, traceable, and attributable.
- ai
- ai-gateway
- enterprise
- gateway
Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.
- ai
- ai-infrastructure
- developer-tools
- llms
移动版二次元 AI 老婆聊天器
WebAI2API: 基于 Camoufox 的网页 AI 转 API 工具,支持 LMArena/Gemini等,多窗口并发与账号隔离。 | Web AI to OpenAI API via Camoufox. Supports LMArena/Gemini and more, multi-window concurrency & account isolation.
Advbox is a toolbox to generate adversarial examples that fool neural networks in PaddlePaddle、PyTorch、Caffe2、MxNet、Keras、TensorFlow and Advbox can benchmark the robustness of machine learning models. Advbox give a command line tool to generate adversarial examples with Zero-Coding.
- adversarial-examples
- paddlepaddle
- machine-learning
- security
Application implementation with business use cases for safely utilizing generative AI in business operations
- aws
- bedrock
- generative-ai
- chatbot
RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.
Multiversal tree writing interface for human-AI collaboration
Agent-native AI assistant — chat, write, whiteboard, learning, all in one.
Local inference that behaves like a frontier API: Qwen3.8-Flash-Next on AMD Strix Halo plus small NPU models, over the OpenAI and Anthropic APIs on one port.
- amd
- gfx1151
- gpu-inference
- hip
LLMs for your CLI
🧠 RepoBrain (formerly Antigravity) — Give your repo a brain. ChatGPT for your codebase: works in Claude Code, Cursor, Codex, Windsurf & more.
Build your own generative UI chatbot using the Vercel AI SDK and Google Gemini
OpenClaw alternative in your pocket
LiveBench: A Challenging, Contamination-Free LLM Benchmark
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
- ai-agents
- developer-tools
- binary-analysis
- ctf
Run 284B DeepSeek-V4-Flash (<59GiB RAM: 41.1 cold pp, 9.1 N=1 tg, up to 25.3 spec tok/s) & 30B MoEs (22.4 N=1 / 111.6 spec tok/s) on 64GB CPU (0 GPUs).